© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8200
    Prev
    Next
    INDEX
    Explanations

    phrases indicating separation or disintegration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hither
    -0.46
    Enlaces
    -0.42
    Cyn
    -0.39
    richTextPanel
    -0.39
     thither
    -0.38
    higher
    -0.38
     propag
    -0.37
     cal
    -0.37
     initWithFrame
    -0.37
    Redraw
    -0.36
    POSITIVE LOGITS
     breakup
    0.55
    <?
    0.52
     écl
    0.52
     breakout
    0.50
    SequentialGroup
    0.50
     splits
    0.50
     appelez
    0.47
     sépar
    0.47
     alugar
    0.47
     Breakout
    0.46
    Activations Density 0.195%

    No Known Activations